CODEWITHSUNDEEP
pythonnlpnltk
taga
taga

Reputation: 3885

Apply NLP WordNetLemmatizer on whole sentence show error with unknown pos

I want to Apply NLP WordNetLemmatizer on whole sentence. The problem is that I get an error:

KeyError: 'NNP'

Its like Im getting unknown 'pos' value, but I do not know why. I want to get base form of the words, but without 'pos' it does not work. Can you tell me what am I doing wrong?

import nltk

from nltk.tokenize import PunktSentenceTokenizer
from nltk.tokenize import word_tokenize
from nltk.tokenize import RegexpTokenizer
from nltk.stem import WordNetLemmatizer 

nltk.download('averaged_perceptron_tagger')

sentence = "I want to find the best way to lemmantize this sentence so that I can see better results of it"

taged_words = nltk.pos_tag(sentence)
print(taged_words)


lemmantised_sentence = []

lemmatizer = WordNetLemmatizer()
for word in taged_words:

     filtered_text_lemmantised =  lemmatizer.lemmatize(word[0], pos=word[1])
     print(filtered_text_lemmantised)

     lemmantised_sentence.append(filtered_text_lemmantised)

lemmantised_sentence = ' '.join(lemmantised_sentence)
print(lemmantised_sentence)

Upvotes: 2

Views: 207

Answers (1)

amipro
amipro

Reputation: 386

The sentence should be split before sending it to pos_tag function. Also, the pos argument differs in what kind of strings it accepts. It only accepts 'N','V' and so on. I have updated your code from this https://stackoverflow.com/a/15590384/7349991.

import nltk

from nltk.tokenize import PunktSentenceTokenizer
from nltk.tokenize import word_tokenize
from nltk.tokenize import RegexpTokenizer
from nltk.stem import WordNetLemmatizer
from nltk.corpus import wordnet

def main():
    nltk.download('averaged_perceptron_tagger')
    nltk.download('wordnet')

    sentence = "I want to find the best way to lemmantize this sentence so that I can see better results of it"

    taged_words = nltk.pos_tag(sentence.split())
    print(taged_words)

    lemmantised_sentence = []


    lemmatizer = WordNetLemmatizer()
    for word in taged_words:
        if word[1]=='':
            continue
        filtered_text_lemmantised = lemmatizer.lemmatize(word[0], pos=get_wordnet_pos(word[1]))
        print(filtered_text_lemmantised)

        lemmantised_sentence.append(filtered_text_lemmantised)

    lemmantised_sentence = ' '.join(lemmantised_sentence)
    print(lemmantised_sentence)

def get_wordnet_pos(treebank_tag):

    if treebank_tag.startswith('J'):
        return wordnet.ADJ
    elif treebank_tag.startswith('V'):
        return wordnet.VERB
    elif treebank_tag.startswith('N'):
        return wordnet.NOUN
    else:
        return wordnet.ADV


if __name__ == '__main__':
    main()

Upvotes: 3

Related Questions